3D Pictorial Structures for Multiple Human Pose Estimation
Authors:
- Vasileios BelagiannisVBVasileios Belagiannis
- Sikandar AminSASikandar Amin
- Mykhaylo AndrilukaMAMykhaylo Andriluka
- Bernt SchieleBSBernt Schiele
- Nassir NavabNNNassir Navab
- Slobodan IlicSISlobodan Ilic
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1669-1676
Abstract
In this work, we address the problem of 3D pose estimation of multiple humans from multiple views. This is a more challenging problem than single human 3D pose estimation due to the much larger state space, partial occlusions as well as across view ambiguities when not knowing the identity of the humans in advance. To address these problems, we first create a reduced state space by triangulation of corresponding body joints obtained from part detectors in pairs of camera views. In order to resolve the ambiguities of wrong and mixed body parts of multiple humans after triangulation and also those coming from false positive body part detections, we introduce a novel 3D pictorial structures (3DPS) model. Our model infers 3D human body configurations from our reduced state space. The 3DPS model is generic and applicable to both single and multiple human pose estimation. In order to compare to the state-of-the art, we first evaluate our method on single human 3D pose estimation on HumanEva-I [22] and KTH Multiview Football Dataset II [8] datasets. Then, we introduce and evaluate our method on two datasets for multiple human 3D pose estimation. In order to compare to the state-of-the art, we first evaluate our method on single human 3D pose estimation on HumanEva-I [22] and KTH Multiview Football Dataset II [8] datasets. Then, we introduce and evaluate our method on two datasets for multiple human 3D pose estimation.Keywords
This publication has 24 references indexed in Scilit:
- Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief PropagationInternational Journal of Computer Vision, 2011
- Real-time human pose recognition in parts from single depth images2011
- Multi-view 3D Human Pose Estimation in Complex EnvironmentInternational Journal of Computer Vision, 2011
- Guest Editorial: State of the Art in Image- and Video-Based Human Pose and Motion EstimationInternational Journal of Computer Vision, 2009
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human MotionInternational Journal of Computer Vision, 2009
- Optimization and Filtering for Human Motion CaptureInternational Journal of Computer Vision, 2008
- A survey of advances in vision-based human motion capture and analysisComputer Vision and Image Understanding, 2006
- Inferring 3D structure with a statistical image-based shape model2003
- The Representation and Matching of Pictorial StructuresIEEE Transactions on Computers, 1973